{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T18:28:50Z","timestamp":1784399330039,"version":"3.55.0"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202058"],"award-info":[{"award-number":["62202058"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/tits.2023.3266487","type":"journal-article","created":{"date-parts":[[2023,4,19]],"date-time":"2023-04-19T17:36:44Z","timestamp":1681925804000},"page":"9984-9995","source":"Crossref","is-referenced-by-count":92,"title":["Multi-Modal Feature Pyramid Transformer for RGB-Infrared Object Detection"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4091-4782","authenticated-orcid":false,"given":"Yaohui","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Beijing Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Computer, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2587-1702","authenticated-orcid":false,"given":"Hua","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.11.017"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811999"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.36"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3076466"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_46"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3099870"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191080"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506322"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_20"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref11","first-page":"1","article-title":"Multispectral pedestrian detection via simultaneous detection and segmentation","author":"li","year":"2018","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3022623"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.73"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.09.015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105143"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00523"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01270"},{"key":"ref51","first-page":"1","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"florian","year":"2017","journal-title":"Proc Comput Vis Pattern Recognit"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_17"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475708"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00299"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350949"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2972974"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3146575"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2479925"},{"key":"ref4","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2020.3027319"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00921"},{"key":"ref40","first-page":"15908","article-title":"Transformer in transformer","author":"han","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"ref31","article-title":"Visual transformers: Token-based image representation and processing for computer vision","author":"wu","year":"2020","journal-title":"arXiv 2006 03677"},{"key":"ref30","first-page":"1","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref33","article-title":"Toward transformer-based object detection","author":"beal","year":"2020","journal-title":"arXiv 2012 09958"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2801560"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3118206"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00012"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.02.005"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.08.005"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3060162"},{"key":"ref20","first-page":"1","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"ref28","article-title":"Multimodal object detection via probabilistic ensembling","author":"chen","year":"2021","journal-title":"arXiv 2104 02904"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.03.007"},{"key":"ref29","first-page":"1","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref62","article-title":"Cross-modality fusion transformer for multispectral object detection","author":"qingyun","year":"2021","journal-title":"arXiv 2111 00273"},{"key":"ref61","first-page":"1","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2017","journal-title":"Proc Int Conf Learn Represent"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/10235283\/10105844.pdf?arnumber=10105844","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T17:56:47Z","timestamp":1744221407000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10105844\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":62,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tits.2023.3266487","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}